S. M. Vovk


Context. Using of the conventional methods of Gaussian decomposition in the case, when the original data are distorted by impulsive
noise, leads to considerable errors. The object of this study is the process of Gaussian decomposition in an impulsive noise environment.
Objective. The goal of this work is the development of a method of Gaussian decomposition for the case when the data are distorted by
impulsive noise.
Method. The proposed method of Gaussian decomposition is based on solving the problem of unconstrained minimization the objective
function by unknown parameters. The problem statement is built on the criterion of a minimum extent which is used to the solution residual.
Process of Gaussian decomposition is implemented iteratively by successive selecting from the sum of Gaussian functions such a Gaussian function, which initially is the most extended, and then the one which is less extended, etc. To determine the parameter values of Gaussian function the two approaches are described. The first approach is based on the iterative method, which is used for solving the set of nonlinear equations, derived from the necessary conditions for the minimum of objective function. The second approach is based on the method of
passive searching of objective function minimum, where the test points are chosen from the condition that in these points the discrepancy is
zero. It is indicated that the second approach has a wider range of applicability than the first one. On the basis of the second approach, an
iterative algorithm is built. The way of selecting the initial parameter values of Gaussian function under impulsive noise environment is
presented. Also, the rule for choosing the best values of Gaussian parameters and the rule to stop of computing are formulated.
Results. Simulations for the problems of the single Gaussian curve fitting to data and of the Gaussian decomposition for the sum of five
Gaussians in the case, when the data are distorted by Cauchy noise, confirmed the performance of the proposed method.
Conclusions. The proposed method is the efficient tool of Gaussian decomposition for the sum of Gaussians distorted by the impulsive
noise with Cauchy distribution. It can be expanded to the case when the functions have other shape and other unknown parameters.


Gaussian decomposition; data processing; extent.


Titchmarsh E. C. The theory of functions / E. C. Titchmarsh. – New York : Oxford University Press, 1939. – 454 p. 2. Borulko V. F. Minimum-duration filtering / V. F. Borulko, S. M. Vovk // Радіоелектроніка, інформатика, управління. – 2016. – № 1. – С. 7–14. DOI: 10.15588/1607-3274-2016-1-1. 3. Vovk S. M. Statement of a problem of definition of linear signals parameters in quasinormed space / S. M. Vovk, V. F. Borul’ko // Radioelectronics and Communications Systems. – 2010. – Vol. 53. – P. 367–375. 4. Goshtasby A. Curve fitting by a sum of Gaussians / A. Goshtasby, W. D. O’Neill // Graphical Models and Image Processing. – 1994. – Vol. 56, No. 4. – P. 281–288. 5. Lindner R. R. Autonomous Gaussian decomposition / [R. R. Lindner, C. Vera-Ciro, C. E. Murray, S. Stanimirovic, B. L. Babler, C. Heiles, P. Hennebelle, W. M. Goss, J. Dickey // The Astronomical Journal. – 2015. – Vol. 149, No. 4. – P. 138–149. DOI: 10.1088/0004-6256/149/4/138. 6. Little M. A. Generalized methods and solvers for noise removal from piecewise constant signals. I. Background theory / M. A. Little, N. S. Jones // Proceedings of the Royal Society A. – 2011. – Vol. 467. – P. 3088–3114. DOI: 10.1098/rspa.2010.0671. 7. Гилат А. MATLAB. Теория и практика / А. Гилат. – М.: ДМК ПРЕСС, 2016. – 416 с. 8. Speyer J. Stochastic Estimation and Control for Linear Systems with Cauchy Noise / J. Speyer, M. Idan, J. Fern ndez // Advances in Estimation, Navigation, and Spacecraft Control. – 2015. – Chapter 6. – P. 95–118. DOI: 10.1007/978-3-662-44785-7_6. 9. Gonzalez J. G. Optimality of the myriad filter in practical impulsive-noise environments / J. G. Gonzalez, G. R. Arce // IEEE Trans. on Signal Processing. – 2001. – Vol. 49, No. 2. – P. 438–441. DOI: 10.1109/78.902126. 10. Aysal T. C. Meridian filtering for robust signal processing / T. C. Aysal, K. E. Barner // IEEE Trans. on Signal Processing. – 2007. – Vol. 55, No. 8. – P. 3949–3962. DOI: 10.1109/TSP.2007.894383.

GOST Style Citations

Copyright (c) 2017 S. M. Vovk

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Address of the journal editorial office:
Editorial office of the journal «Radio Electronics, Computer Science, Control»,
National University "Zaporizhzhia Polytechnic", 
Zhukovskogo street, 64, Zaporizhzhia, 69063, Ukraine. 
Telephone: +38-061-769-82-96 – the Editing and Publishing Department.

The reference to the journal is obligatory in the cases of complete or partial use of its materials.